Research
My research interests are broadly in the areas of machine learning and optimization. Particularly, I am interested in the theoretical
and practical problems that arise when deploying data driven techniques in real world settings such as education and healthcare.
Currently, my research focuses on problems related to intelligent tutoring systems including deep learning for student performance
predictions and reinforcement learning for personalized curriculum design.
|
|
Transferable Student Performance Modeling for Intelligent Tutoring Systems
Robin Schmucker,
Tom M. Mitchell
Accepted at ICCE, 2022
We propose transfer learning techniques that can mitigate the student
performance modeling cold-start problem for new courses by leveraging
log data from existing courses. Our course-agnostic
models enable accurate predictions for future courses when they are first deployed.
|
|
Assessing the Performance of Online Students - New Data, New Approaches, Improved Accuracy
Robin Schmucker,
Jingbo Wang,
Shijia Hu,
Tom M. Mitchell
Journal of Educational Data Mining, 2022
Video, GitHub
We study how to utilize various types of student
log data for performance modeling using four recent large-scale
datasets. We propose various extensions over earlier methods and
define a new state of the art for logistic regression-based performance modeling.
|
|
Combination Treatment Optimization Using a Pan-Cancer Pathway Model
Robin Schmucker,
Gabriele Farina,
James Faeder,
Fabian Fröhlich,
Ali Sinan Saglam,
Tuomas Sandholm
PLOS Computational Biology, 2021
We use a pan-cancer pathway model to identify novel combination
therapies by defining multiple treatment optimization problems and solving
them by combining CMA-ES with an efficient Hamiltonian Monte-Carlo sampling scheme.
We also consider sequential treatment plans.
|
|
Multi-objective Asynchronous Successive Halving
Robin Schmucker,
Michele Donini,
Muhammad Bilal Zafar,
David Salinas,
Cédric Archambeau
arXiv, 2021
We propose multiple algorithms that extend ASHA to the multi-objective
hyperparameter optimization (HPO) setting. We assess the performance of
our methods on various real world tasks related to neural architecture search,
algorithmic fairness, and language model optimization.
|
|
Fair Bayesian Optimization
Valerio Perrone,
Michele Donini,
Muhammad Bilal Zafar,
Robin Schmucker,
Krishnaram Kenthapadi,
Cédric Archambeau
AAAI/ACM Conference on AI, Ethics, and Society (AIES), 2021
We introduce a general constrained Bayesian optimization framework
to optimize the performance of any ML model while enforcing different
fairness constraints. Our approach is competitive with
techniques that enforce model-specific constraints and ones that learn fair representations ahead of time.
|
|
Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games
Gabriele Farina,
Robin Schmucker,
Tuomas Sandholm
AAAI Conference on Artificial Intelligence, 2021
We propose the first algorithm for the bandit linear optimization problem for
tree-form sequential decision making that offers both (i) linear-time iterations
(in the size of the decision tree) and (ii) O(√T) cumulative regret in
expectation compared to any fixed strategy, at all times T.
|
|
Multi-Objective Multi-Fidelity Hyperparameter
Optimization with Application to Fairness
Robin Schmucker,
Michele Donini,
Valerio Perrone,
Muhammad Bilal Zafar,
Cédric Archambeau
NeurIPS Workshop on Meta-Learning, 2020
We study the suitability of existing multi-objective algorithms
for ML hyperparameter optimization and propose a novel multi-fidelity method.
We evaluate on multiple fairness-motivated applications
and achieve lower wall-clock times
when approximating Pareto frontiers.
|
|
Counterfactual-Free Regret Minimization for Sequential Decision Making and
Extensive-Form Games
Gabriele Farina,
Robin Schmucker,
Tuomas Sandholm
AAAI Workshop on Reinforcement Learning in Games, 2020
We propose the first efficient regret minimization algorithm for the
bandit linear optimization problem on sequential decision processes and
extensive-form games and show that it achieves O(√T)
cumulative regret in expectation against any strategy.
|
|
Towards a Robust Interactive and Learning Social Robot
Michiel de Jong,
Kevin Zhang,
Aaron M. Roth,
Travers Rhodes,
Robin Schmucker,
Chenghui Zhou,
Sofia Ferreira,
João Cartucho,
Manuela Veloso
Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2018
We augment Pepper's perception by integrating state-of-the-art vision and speech recognition systems.
As we recognize limitations of the individual perceptual modalities, we introduce a
multi-modality approach to increase the robustness of human social
interaction with the robot. We combine vision, gesture, speech, and
input from an onboard tablet, a remote mobile phone, and external
microphones.
|
|
Multimodal Movement Activity Recognition Using a Robot’s Proprioceptive Sensors
Robin Schmucker,
Chenghui Zhou,
Manuela Veloso
RoboCup 2018: Robot World Cup XXII, 2018
By introducing Human Activity Recognition approaches to the robotics domain,
we aim at creating agents that can detect their own body’s activities.
Our activity recognition pipeline can detect unexpected behavior and can
be used to extend Pepper’s inbuilt capabilities.
|
|
A universal test for gravitational decoherence
C. Pfister,
J. Kaniewski,
M. Tomamichel,
A. Mantri,
R. Schmucker,
N. McMahon,
G. Milburn,
S. Wehner
Nature Communications, 2016
Quantum mechanics (QM) and the theory of gravity are presently not compatible.
One question is whether gravity causes decoherence. We propose
a method to estimate gravitational decoherence in an experiment that
can draw conclusions in any physical theory where the no-signalling
principle holds, even if QM needs to be modified.
|
Template of this page: link.
|
|